Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    substit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Codes
    -0.07
    도를
    -0.07
    .metamodel
    -0.06
    ESSAGE
    -0.06
     kraje
    -0.06
     madre
    -0.06
    _points
    -0.06
     crank
    -0.06
     труда
    -0.06
    movies
    -0.06
    POSITIVE LOGITS
     substit
    0.07
     chaque
    0.07
     Scr
    0.06
    悉
    0.06
     sake
    0.06
    opl
    0.06
     nightly
    0.06
    ResourceManager
    0.06
     ses
    0.06
     Ac
    0.06
    Act Density 0.002%

    No Known Activations